LogoAhaPrompt
  • 提示詞
  • 精選
  • 模型
  • AI 反推
  • 定價
  • 投稿
  • 部落格
AhaPrompt

圖片、影片、音訊 AI 提示詞庫

探索

  • 全部提示詞
  • 精選提示詞
  • 圖片提示詞
  • 影片提示詞
  • 音訊提示詞
  • AI 模型

工具

  • AI 反推工作臺
  • 圖片反推提示詞
  • 影片反推提示詞

資源

  • 定價方案
  • 投稿提示詞
  • 部落格

版權所有 © 2026 AhaPrompt 保留所有權利。

隱私政策條款與條件退款政策版權申訴 / DMCA
首頁AI 提示詞庫AI 影片提示詞古风女侠合影恶作剧

古风女侠合影恶作剧

ByteDanceSeedance 2.5ByteDancevideo

【整体风格与核心故事】 严格30秒,16:9横屏,Seedance 2.5,真人电影级古风仙侠反转喜剧,原生普通话音画同步。 作品:《说好的合影呢?》 整体采用真实自然的中国古风影视美学,细腻肤质、真实丝绸衣料、自然体积光、丰富环境纵深和克制的人物表演。 借鉴经典视觉喜剧中的信息差、物体运用、行为重复与角色互换,以及现实生活中为了拍出一张满意的照片而不断折腾身边人的熟悉情境。 主线非常明确: 小师妹原本想和师姐一起留下一张好看的合影。 白衣师姐却过分在意自己在画面中是否完美。 她不断让小师妹举起铜镜、调整方向、寻找合适光线,逐渐把小师妹变成了自己的专属补光助手。 观众比小师妹更早意识到,这张所谓的“合影”实际上只有师姐一个人。 拍完以后,小师妹发现画面里只有自己举镜子的那只手。 师姐竟然还一本正经地解释“手拍得挺好”。 小师妹没有争吵,而是把铜镜交到师姐手里,让师姐亲自体验刚才的过程。 最后一个镜头完全呼应开头,只交换两个人的位置与身份。 核心喜剧来自: 认真得过分的师姐; 逐渐察觉问题的小师妹; 一个人追求出片,另一个人被迫承担全部辅助工作的生活反差; 以及最后精确对称的角色互换。 不加入反派寻仇、师父拆台、突然战斗、随机魔法或无关反转。 【人物与人物关系】 角色ID A:同一个@图片1剑仙师姐。 25–30岁成年东亚女性,保持参考图中完全相同的人脸身份、五官骨相、肤质、比例、气质和发型。 高挑纤细,黑色长发半挽,白玉簪固定,始终穿白色刺绣真丝汉服、分层半透明宽袖、银色腰封、玉佩及白色布靴,持唯一一柄银色长剑。 性格冷静、端庄、自信,平时看起来不在乎外表,实际上对自己的形象相当讲究。 面对留影这件事,她甚至像研究剑法一样认真安排角度、姿势与光线。 角色ID B:同一个@图片2小师妹。 20–25岁成年东亚女性,保持参考图中完全相同的人脸身份、五官、面部比例、编发、体型和气质。 身形娇小,五官自然圆润灵动,穿同一套青绿色亚麻汉服、深色腰带、木簪和黑色布鞋,持唯一一柄深色钢剑。 性格直率、善于观察,开始时愿意帮师姐完成拍摄。 当她明白自己被当成举镜子的助手以后,不发火、不撒泼,只以同样的方式让师姐体验一次。 本集只有这两名核心人物,不额外增加师父、敌人或其他主要角色。 关键道具为一面直径约30厘米的古代抛光铜镜,以及一枚稳定放在石台上的仙侠留影石。 铜镜依靠真实自然光反射补光,有实际重量,始终由人物双手或单手合理握持。 留影石只用短促、柔和的灵光完成一次静态留影,不出现现代相机、电子屏幕或复杂法术界面。 【当前地点与空间连续性】 本轮新上传的所有背景与地点参考图共同决定视频的实际物理世界。 先无声提炼并整合参考图中能够兼容的真实地形、主要建筑关系、空间尺度、材质、植被、水体、天气、云层、山雾、主光方向、色彩、倒影和空气纵深。 重新组合为本轮独有、合理、连续的实际场景。 在这些真实空间中选择一处适合留影、可以安全站立的观景平台或庭院石台;如果参考图没有相应平台,就使用参考世界里真实存在、可供人物活动的位置。 绝不能凭空替换成陌生的泛化仙侠场景。 整段故事发生在同一个位置。 留影石固定在一个稳定石座上,面向师姐原本所站的位置。 师姐最初站在画面中央。 小师妹站在画面边缘,举起铜镜,将自然光柔和地反射到师姐脸上。 小师妹身体大部分处于留影石取景范围之外,只有举着铜镜的手和铜镜边缘刚好进入画面。 这种真实的几何位置必须从开头一直保留到反转揭示,不能为了笑点突然改变。 背景始终自然鲜活: 风吹动头发和衣袖; 树叶随风轻摆; 已有水体持续流动; 山雾按照真实地势缓慢变化; 光影和倒影随着摄影机视角合理变化。 但这些环境运动保持叙事中立,不主动推动或改变剧情。 【0–4秒:开场钩子】 开场首先给出一个非常漂亮的电影级中远景构图。 同一个白衣师姐站在参考图形成的壮阔自然空间中。 她姿态优雅,腰侧银色长剑自然垂落,浅色真丝宽袖被微风轻轻吹动。 初看仿佛一张真正绝美、庄严的剑仙电影剧照。 然而摄影机立刻进行一次小幅度、精准的横向移动。 画面旁边突然露出同一个青衣小师妹。 小师妹正吃力地高举一面铜镜,手臂已经开始发酸。 她看向师姐: 小师妹:“师姐,说好的合影呢?” 师姐甚至没有转头,只看着留影石的位置: 师姐:“镜子再抬高点。” 原本庄严的剑仙画面,瞬间变成一场让人十分熟悉的拍照折腾现场。 【4–10秒:人物目标与铺垫】 保持同一位置、同一面铜镜以及两人的真实空间关系。 中景双人镜头。 小师妹把铜镜举得更高一点。 师姐认真观察反射到自己脸上的柔和光线,轻轻移动下巴,又整理一缕头发。 师姐:“往左一点。” 小师妹按照要求移动手臂。 师姐:“再高一点。” 小师妹再次照做。 镜子有实际重量,她抬着的手臂已经明显开始疲劳。 小师妹终于有些疑惑: 小师妹:“师姐,我也入画了吗?” 师姐看了一眼留影石的取景方向。 她已经注意到小师妹大部分身体并没有进入画面。 短暂停顿。 师姐仍然非常平静: 师姐:“入了,放心。” 小师妹暂时选择相信。 师姐脸上那一点极其细微的不自然,让观众开始意识到她心里其实很清楚。 【10–18秒:喜剧冲突升级】 仍然保持完全相同的地点、人物和道具关系。 师姐先稍微转动身体寻找更适合面部的光线,再调整银色长剑的角度,使自己的整体轮廓更加优雅。 她只改变两次姿态。 但每次调整,都需要小师妹重新改变铜镜角度,才能让反射光保持稳定。 镜头不使用快速蒙太奇,而是完整记录两次连续、合理的动作。 小师妹一边举着铜镜,一边尝试把脑袋伸入留影石的取景范围,希望自己也能出现在合影里。 师姐立即轻轻提醒: 师姐:“别晃,马上好了。” 小师妹只好停住。 她保持着一个越来越不舒服的举镜姿势。 此刻给出一个留影石实际取景方向的客观镜头。 观众可以清楚看见: 画面中央是姿态完美的白衣师姐。 画面边缘只露出小师妹举铜镜的手和一点铜镜边框。 小师妹的脸和身体完全不在画面里。 这一镜头必须让观众先于角色理解最终的笑点。 留影石只发出一次极其柔和的短促灵光,完成静态留影。 不产生夸张魔法。 【18–25秒:关键变化与反转】 留影结束。 师姐终于放松姿态: 师姐:“成了。” 小师妹立即放下已经发酸的手臂,走到留影石旁边查看刚才的画面。 摄影机先保持自然的双人中景,再短暂展示刚刚记录的构图。 留影结果与之前取景镜头完全一致: 师姐漂亮地站在中央。 小师妹只有一只举镜子的手出现在画面边缘。 不出现任何文字。 小师妹认真看了一眼。 停顿半拍。 小师妹:“我呢?” 师姐非常认真地伸手指向画面边缘那只手。 师姐:“这儿,手拍得挺好。” 小师妹缓慢转头看向师姐。 小师妹:“你管这叫合影?” 师姐原本自信的表情第一次出现明显迟疑。 她看看留影画面,再看看小师妹。 终于意识到自己的解释听起来实在有些不像话。 不要让她继续狡辩,也不要增加第三人说话。 这一段的笑点依靠清楚的视觉证据、师姐一本正经的回答和小师妹的表情成立。 【25–30秒:笑点回收与结尾】 小师妹没有继续争论。 她只是非常自然地把铜镜交到师姐手里。 小师妹:“行,换你举。” 师姐下意识接过铜镜。 小师妹已经走到刚才师姐所站的画面中央。 她轻轻整理青绿色衣袖,摆出一个自然舒展、确实很好看的古风姿态。 师姐此时只能站在画面旁边,像刚才小师妹那样举起铜镜。 摄影机重新回到几乎与开头一模一样的构图。 但这次发生了完全对称的角色互换: 中央是漂亮的青衣小师妹。 边缘是高举铜镜的白衣师姐。 小师妹看向师姐,用几乎完全相同的平静语气说道: 小师妹:“镜子再抬高点。” 师姐看向小师妹。 又看看自己举着的铜镜。 她终于明白,小师妹打算把刚才的待遇原样还给自己。 师姐轻轻叹了一口气。 只能认命地把铜镜再抬高一点。 在这个与开场严格呼应、两人地位完全交换的电影画面上精准结束。 不再增加师父补刀、不追加解释、不出现额外突发事件。 【演员表演与喜剧节奏】 师姐从头到尾都要认真对待这件小事。 她的笑点来自一个明明很在意自己形象,却始终表现得端庄得体的人。 小师妹从信任、配合,到怀疑、发现真相,最后冷静反击,情绪必须连续发展。 手臂疲劳逐步加重,但不使用夸张颤抖、摔倒或者卡通动作。 关键停顿包括: 师姐回答“入了,放心”之前的极短迟疑; 留影画面揭示之后小师妹的半拍沉默; 师姐说出“手拍得挺好”后的尴尬; 最后师姐被迫举镜时的无奈。 所有反应自然可信。 【摄影机与剪辑】 开场采用电影级优美中远景,再通过小幅横移揭示举镜的小师妹,让观众快速重新理解画面。 铺垫使用双人中景,清楚交代空间关系。 递进段落通过铜镜、手臂、剑身、脸部反光等适量细节镜头展现实际动作,但不使用连续碎切。 留影石取景镜头作为核心视觉信息,必须明确展示谁在画面里、谁在画面外。 反转通过人物查看留影结果和表情变化完成。 最后采用与开场相互呼应的对称构图,使观众在无需额外解释的情况下理解角色互换。 镜头变化自然,不环绕炫技,不随意切换环境。 【普通话对白与声音设计】 全部使用自然普通话。 实际人物台词与英文部分保持完全一致。 师姐声音清雅、镇定,语速正常,不故作高冷。 小师妹声音灵动,前半段配合,后半段逐渐出现疑惑和不满,最后恢复平静,带着一点小小的得意。 同一时间只允许一个人物说话。 说话人物口型准确;非说话人物闭嘴,用真实眼神和微表情回应。 背景音为自然风声、远处流水、布料摩擦、铜镜轻响、人物脚步以及一次轻微的留影石灵光声。 配乐极轻,在视觉揭示和最终角色互换时适当退去。 不要罐头笑声,不生成画面字幕或可读文字。 【人物、道具及环境连续性】 师姐、小师妹始终保持图一和图二对应的人脸身份、发型、身材、服装和武器。 全片只有一面铜镜和一枚留影石。 铜镜的实际位置、镜面方向、人物握持方法和反射光线必须相互匹配。 小师妹举镜动作必须符合正常人体活动范围。 师姐的银剑与小师妹的深色钢剑不能交换。 留影石拍下的图像必须与之前展示的实际取景构图一致。 同一地点、地形、建筑、树木、水体、主光方向、天气和空间层次保持连续。 【Seedance 2.5执行要求】 严格30秒,16:9横屏。 优先一次生成完整故事,按照0–4秒、4–10秒、10–18秒、18–25秒、25–30秒五个段落组织。 充分利用 Seedance 2.5 的多人物动作一致性、多参考素材控制、连续镜头叙事与原生音视频生成能力。 镜头可以根据故事需要合理切换,但所有动作和道具状态必须连续。 不加入多余人物、台词、特效、剧情和新地点。 真正的笑点必须清楚呈现在画面里。 最后以人物位置互换完成视觉回收,既构成完整结局,也保留两名女主角未来继续发展关系喜剧的空间。 【Negative Prompt】 blurry, bad quality, low quality, low resolution, noisy, jpeg artifacts, watermark, text, error; deformed, mutated, bad anatomy, poorly drawn hands, bad composition, out of frame, disfigured; inconsistent character, changing clothes, face morphing, background shift, glitching cuts, disappearing props

詳細資訊
类型
AI 影片提示詞
畫面比例
16:9
Duration
0:30
更新於
2026年11月12日
分類
CharacterCinematicFantasy
Source

如何使用這條提示詞

  1. 1點選上方複製按鈕,複製完整提示詞。
  2. 2開啟 ByteDance 的 Seedance 2.5,或你常用的 AI 影片生成工具。
  3. 3貼上提示詞,保留鏡頭與運動描述詞——它們決定了畫面的運鏡效果。
  4. 4按示例參數(16:9 · 0:30 · Character · Cinematic · Fantasy)生成,再小步迭代——措辭的細微變化會顯著影響結果。

常見問題

這段影片是用哪個 AI 模型生成的?

本片段由 ByteDance 的 Seedance 2.5 生成,頁面上的提示詞就是生成它的原始文字。

這條提示詞用了哪些參數?

示例由 Seedance 2.5 生成,參數:16:9 · 0:30 · Character · Cinematic · Fantasy。沿用這些參數可獲得最接近的效果。

怎樣才能生成相似的效果?

先原樣複製提示詞,只改主體、保留鏡頭/運動/光影描述。影片模型對措辭很敏感,多試幾次為佳。

可以修改這條提示詞嗎?

當然可以。提示詞最適合作為起點——替換場景、調整節奏詞或寬高比,適配你的專案。

更多 Seedance 2.5 提示詞

0:30
ByteDanceSeedance 2.5
STYLE: Hollywood disaster-action film, photorealistic live-action, ARRI Alexa 35, anamorphic cinematic lens, realistic Malaysian metropolitan city, practical stunt realism, believable destruction and debris physics, aggressive handheld tracking, natural lighting, cinematic contrast, motion blur, dust, shattered glass, sparks, immersive disaster sound. MAIN CHARACTER: Use Image 1. Maintain exact facial identity, hairstyle, clothing and continuity throughout. CORE RULE: ONE CONTINUOUS SURVIVAL SHOT. No teleportation or unexplained cuts. Every movement logically connects. The man constantly runs, stumbles, recovers, jumps, slides, climbs and changes direction. The environment is the antagonist. 00:00–00:03- EARTHQUAKE Low-angle tracking behind his feet as he runs through a Malaysian city street. Ground violently shakes, he nearly falls, buildings shake and glass explodes. Concrete crashes behind him. He looks back briefly and accelerates. 00:03–00:06- COLLAPSE Front tracking shot racing backward. Building façade collapses behind him. He sharply changes direction, jumps over a metal barrier as concrete blocks destroy his original path. Dust fills the street. 00:06–00:09- CAR IMPACT He reaches an intersection. Vehicles slide uncontrollably toward him. He dives at the last second. Camera dives with him. A car passes overhead. He rolls, immediately gets up and keeps running. 00:09–00:12-ROAD CRACK A huge fissure tears across the road. He runs onto a damaged car, uses it as a springboard and leaps across the collapsing pavement. Lands hard and continues running. 00:12–00:15- FALLING GLASS Side tracking shot. High-rise windows explode above him. Glass rains down. He shields his face, ducks beneath a falling metal sign and keeps moving. 00:15–00:18-COLLAPSE A building front collapses ahead. He spots a narrow gap beneath the debris, drops low and slides underneath. Concrete crashes above him. He emerges dusty and immediately runs. 00:18–00:21-VEHICLE CHAOS A bus crashes into cars. A spinning vehicle comes toward him. He jumps onto its hood, springs off the roof and lands on the opposite sidewalk as sparks erupt behind him. 00:21–00:24- ELEVATED ROAD FAILURE An elevated roadway breaks apart ahead. He sprints to the edge and performs a full-body gap jump over the collapsing section. Brief dramatic slow motion, then real-time. Hard landing, roll, recover, run. 00:24–00:27- DEBRIS CHASE Heavy dust reduces visibility. Close shoulder-level pursuit. Falling streetlights and concrete force sudden direction changes. He stumbles against a wall, pushes himself forward and keeps running. A distant vehicle explosion sends a dust shockwave toward him. 00:27–00:30- FINAL COLLAPSE Camera moves ahead, facing him. Massive buildings collapse behind him as he runs toward camera. He jumps over a concrete barrier. A gigantic slab crashes behind him, creating a huge dust cloud. He emerges through the dust still running. CUT TO BLACK. One final footstep. SOUND: Deep earthquake rumble, structural cracking, glass explosions, crowd panic, tires, metal impacts, concrete crashes, heavy breathing, sparks, distant explosion and final low-frequency collapse. PERFORMANCE: He behaves like a real person fighting to survive not an action hero posing. Fear, instinct and adrenaline control every reaction. Realistic balance, impacts and recovery. CAMERA: Low tracking, front pursuit, side tracking, shoulder-mounted chase, whip-pans, ground-level slides and brief airborne follow shots. Camera always follows his momentum. No random drone shots, floating cameras or impossible rotations. FINAL FEEL: Relentless 30-second survival adrenaline — RUN → COLLAPSE → EVADE → JUMP → IMPACT → RECOVER → RUN → BIGGER COLLAPSE → RUN. Duration: 30 seconds | Aspect Ratio: 16:9
檢視詳情
0:30
ByteDanceSeedance 2.5
Photorealistic Hollywood supernatural horror short film, shot on 35mm anamorphic lenses with natural film grain, shallow depth of field and practical lighting. Opens with an instant scare, no establishing shot. Setting: an isolated lakeside cabin at night in heavy rain and thunderstorm, rustic wood interior, one flickering table lamp, dying fireplace embers, a cellar door in the kitchen. CHARACTER LOCK: Claire is a woman in her late 20s with shoulder-length auburn hair, an oversized gray knit sweater, jeans and dark socks, identical in every shot. A framed photo of her late mother sits on the mantel. The creature is original: a very tall, gaunt, gray-skinned humanoid with unnaturally long arms and fingers, joints that bend slightly wrong, long wet black hair hanging over a smooth blank face with only a thin dark seam where a mouth should be. It moves in quick, stuttering bursts and mimics human voices perfectly. Practical-effects look. No blood, no gore. Cold blue storm light against warm amber lamp glow, natural diegetic sound, low string drone from the first frame. No text overlay, no watermark. [0-1s] Hard cut: the cellar door in the kitchen bangs open on its own, rain hammering the windows, the lamp flickering. [1-2s] Close-up: Claire freezes on the sofa, her mug slipping from her hand and shattering on the floorboards. [2-3s] From the dark cellar, her late mother’s warm voice calls softly: “Claire? Sweetheart, come down here.” [3-4s] Extreme close-up: Claire’s eyes fill with tears and dread, the mother’s photograph blurred behind her. [4-5s] Slow dolly shot down the hallway toward the cellar as she grabs a flashlight from a hook. [5-6s] Over-the-shoulder: she steps onto the first stair, wood creaking, the beam trembling. [6-7s] POV down the steps: the flashlight finds wet footprints on the concrete, far too long and narrow to be human. [7-8s] Close-up: she whispers, “Mom?” and her own voice answers “Mom?” from right behind her. [8-9s] Whip-pan: nothing behind her but the empty stairwell. [9-10s] Wide shot: in the far corner of the cellar, a tall gaunt figure stands with its head bowed, hair hanging. [10-11s] The flashlight flickers and the figure is suddenly halfway across the room. [11-12s] Close-up: its head lifts, the hair parting to show the smooth blank face and the thin dark seam. The mother’s voice comes from it: “Claire.” [12-13s] Handheld: she bolts up the stairs, long fingers scraping the steps behind her. [13-14s] Low-angle: she bursts into the kitchen, spins and slams the cellar door, throwing her whole weight against it. [14-15s] Close-up: three heavy thuds bow the wood, and the mother’s voice sobs through the gap: “Claire, please, I’m cold.” [15-16s] Close-up: tears on her face as her trembling hand slides the deadbolt home. [16-17s] She drags the heavy oak kitchen table across the floor against the door. [17-18s] The thuds stop. Silence except for rain, her ragged breathing, and a distant thunder roll. [18-19s] Wide shot: she backs away from the door, listening. [19-20s] Lightning flash: through the kitchen window, the exterior cellar hatch in the yard stands flung open and empty. [20-21s] Close-up: her eyes widen as she realizes it never needed the door. [21-22s] She grabs her car keys and sprints for the front door. [22-23s] Tracking shot: she runs across the muddy yard in the rain toward her car, headlights blinding the lens. [23-24s] Interior car: she locks the doors and fumbles the key into the ignition, the engine roaring to life. [24-25s] The car lurches down the dirt road, the cabin shrinking in the rearview mirror. [25-26s] Close-up: wipers sweeping, radio static, her breath slowing into a tearful, relieved laugh. [26-27s] Close-up in the rearview mirror: the back seat is empty. She exhales. [27-28s] The radio static swells and a soft voice whispers from the back seat in her mother’s tone: “Don’t leave me again.” [28-29s] Extreme close-up: her eyes lock on the mirror as a long, pale hand slowly settles on the headrest behind her. [29-30s] Smash cut to black with a hard sound sting. Audio: storm rain and thunder, creaking wood, a low string drone and heartbeat pulses that drop to near-silence in the quiet beats, mimicked voices with a faint unnatural echo, car engine and wipers, a sharp stinger on the final cut. Camera: slow dolly pushes, whip-pans, low angles, handheld on the chase, extreme close-ups. Realistic shake only on impacts.
檢視詳情
0:15
ByteDanceSeedance 2.5
Create a 15-second ultra-realistic lifestyle video in vertical 9:16 format, using the attached image as the visual reference for the woman's appearance, outfit, car interior, lighting, and overall aesthetic. SCENE AND ACTION: 0-3 seconds: The video starts mid-action. The woman is getting into the driver's seat of the parked car. She pulls her second leg inside, settles into the seat, and firmly closes the driver's door. Capture the natural movement of her body and the door closing with a realistic thud. 3-6 seconds: From a natural passenger-side interior angle, she adjusts herself comfortably in the seat, takes off her sunglasses, and places them beside her handbag. 6-10 seconds: She reaches for her iced green matcha drink, lifts it naturally, takes a relaxed sip through the straw, and lowers the cup. 10-15 seconds: She gazes out of the side window, enjoying a quiet moment. Soft natural sunlight falls across her face and the car interior. End with her relaxed, holding the drink. VISUAL STYLE: Authentic, ultra-realistic smartphone lifestyle footage. Natural skin texture, realistic facial features, believable body movements, accurate hands and fingers, natural hair movement, physically accurate lighting and reflections, and consistent character appearance throughout. CAMERA: Natural handheld smartphone perspective with subtle movement. Use a smooth, believable transition from the exterior door-closing moment to the interior shot. Avoid dramatic camera movements or artificial cinematic effects. AUDIO: Natural car-door closing sound, subtle parking-lot ambience, and realistic drink-handling sounds only. Leave out voiceover, captions, on-screen text and music. IMPORTANT: The car remains parked and stationary. Do not show her walking toward the car. Do not change her face, hairstyle, outfit, drink, or car interior. Avoid distorted hands, warped objects, artificial skin, exaggerated expressions, or unnatural movements.
檢視詳情
0:30
ByteDanceSeedance 2.5
Multi-shot sequence with hard cuts between shots. Keep the same characters and visual style throughout. No music or score — only natural diegetic sound. SHOT 1 A dirty, exhausted 18-year-old girl with dark auburn-brown hair in a messy low ponytail, warm brown eyes, faded olive-green military jacket, backpack and gloves, aims a bolt-action rifle inside an abandoned ornate mansion. Sweat, dirt, a cheek scrape and tears cover her face. Her hands tremble. She closes her eyes as a tear rolls down, then hears something and lowers the rifle, visibly heartbroken. SHOT 2 Over her shoulder, an infected golden-coated Golden Retriever sits on the debris-covered parquet floor. Matted fur, cloudy white eyes, wounds and dark veins. He trembles while softly whimpering and growling. SHOT 3 She slowly crouches, places the rifle on the floor, wipes her tears and gives the dog a small broken smile. She quietly speaks to him, pulls a worn yellow-green tennis ball from her jacket and gently rolls it toward him. SHOT 4 Extreme low-angle close-up of the tennis ball rolling through dust across the cracked parquet floor. It stops directly in front of the dog's paws. Hold on the still ball. HARD CUT / TRANSFORMATION SHOT 5 Same low camera angle and ball position, but now on a clean sunny residential basketball court. A healthy golden-coated Golden Retriever suddenly grabs the ball. His eyes are clear and warm brown, fur clean, playful and energetic. He shakes and plays with the ball. SHOT 6 Wide shot of the basketball court. The woman throws the ball and the happy dog sprints after it, catches it, runs back and drops it at her feet, ready to play. SHOT 7 Close-up of the clean, unharmed woman laughing while affectionately ruffling the dog's neck and chest. The dog happily pants beside her. SHOT 8 Wide peaceful shot. The woman and dog sit together in a pristine dark-green vintage convertible beside the court. She shares food from a tin can with him. He gently takes it and licks her fingers. CONSISTENCY Same woman throughout: dark auburn-brown hair, loose low ponytail, warm brown eyes, olive-green military jacket, khaki cargo pants and brown boots. Same Golden Retriever: infected and injured in the mansion, healthy and playful after the transformation. Mansion: abandoned ornate interior, tall arched windows, torn dark-red curtains, peeling damask wallpaper, shattered gilt mirror, broken furniture, debris, ceiling hole and strong sunlight beams. Court: clean residential basketball court, white lines, iron fence, flowering shrubs, stone townhouses, warm late-afternoon sunlight and soft shadows. Dark-green vintage convertible with chrome trim. Visual style: ultra-realistic, photorealistic, natural human and animal movement, handheld camera, shallow depth of field, ARRI Alexa 35 look, warm cinematic grade, subtle grain. Audio: ONLY natural breathing, house ambience, dog sounds, footsteps, ball sounds, birds and wind. ABSOLUTELY NO MUSIC OR SCORE.
檢視詳情
0:20
ByteDanceSeedance 2.5
Image1=后方持枪女人;Image2=前景接饮料女人。严格保持两人的脸、发型、服装和身份一致,不得互换。 生成 20秒、16:9、真人电影实拍、一镜到底、无BGM 的犯罪悬疑冷幽默短片。 现代冷灰色室内饮料区,银色饮料机、冷白顶灯。摄影机固定在饮料机侧前方近距离偏低机位,约腰胸高度,35–50mm,中近景,轻浅景深,基本不移动。 0–4s Image2角色B小心靠近饮料机,动作克制自然,只短暂警觉观察一次,表情中性,不微笑。 4–7s 她拿透明塑料杯放到饮料出口下,只用余光确认一次侧后方,随后专注杯子。 7–12s 橙黄色饮料流入杯中并逐渐装满,机器没有及时停止。饮料必须真实超过杯口→沿杯壁流下→流过手指→滴落飞溅到金属托盘。 B只轻微皱眉、抿嘴、手指收紧,出现不到1秒的“糟了”反应,不夸张。 12–14s|关键反转 摄影机不寻找危险。 一把黑色手枪先从B右后方缓慢进入原有画面,枪口靠近她头部侧后方;此时角色A不要立刻完整出现。 B察觉后:眼神先停止→极轻微向右后确认→表情瞬间安静,身体冻结。 不要瞪眼、张嘴、尖叫、猛回头。 14–17s B保持朝向饮料机,非常缓慢地停止处理杯子并逐渐举起双手。 摄影机位置不变,开始一次自然 cinematic rack focus:前景B逐渐失焦,右后方A逐渐清晰。 17–20s Image1角色A成为清晰主体:黑色长直发、金色长耳环、黑色连体泳装,单手稳定持枪,表情完全平静中性,不冷笑、不做凶狠脸。 她看着B,用普通交谈般的低声、平静、认真语气说: “你知道的太多了。” B继续举手,不回头、不回答,只出现极细微眼神停顿。 对白最后一个字结束,画面立即结束。 表演原则: B:克制警觉 → 高度专注 → 短暂迟疑 → 瞬间冻结。危险越大,表演越少。 A:始终平静、稳定、中性,威胁来自持枪行为而不是表情。 **声音:**只有真实同期声:脚步、塑料杯、饮料机、液体流动与溢出、金属托盘飞溅声、衣料声、最后中文对白。无音乐、无恐怖音效、无上膛音。
檢視詳情
0:29
ByteDanceSeedance 2.5
Create a 30-second ultra-realistic cinematic travel vlog featuring a young woman with shoulder-length auburn hair, wearing an elegant cream blazer and matching trousers, carrying a beige canvas tote bag with black printed graphics. Maintain consistent facial features, hairstyle, outfit, and bag throughout the entire video. Scene 1 — European Café Entrance (0–5 seconds): The woman stands outside a charming European café with tall dark teal wooden doors. She casually checks her smartphone, then puts it away and walks inside. Warm café lighting contrasts beautifully with the cool teal doorway. Natural candid movements and subtle handheld camera motion. Scene 2 — Exploring Charming Streets (5–12 seconds): Follow her from behind as she walks through narrow cobblestone streets lined with historic European buildings, outdoor cafés, and small artisan shops. She passes colorful ceramic displays and busy café terraces. Her auburn hair moves gently as she walks, while the tote bag swings naturally at her side. Scene 3 — Sunny Mediterranean Beach (12–20 seconds): Seamlessly transition to a beautiful Mediterranean beach with turquoise water and golden sunlight. Film her walking toward the shoreline from behind. A gentle sea breeze moves her hair and blazer. She pauses beside the waves, turns toward the camera, and smiles naturally. Scene 4 — Golden-Hour Beach Portrait (20–25 seconds): Capture an intimate over-the-shoulder shot as she looks toward the ocean, then turns back with a soft, genuine smile. Warm sunlight illuminates her auburn hair, creating a natural golden rim light. Use shallow depth of field and subtle cinematic lens flare. Scene 5 — Peaceful Sunset Ending (25–30 seconds): A wide cinematic shot reveals the woman sitting on a beach blanket, holding a clear drink while watching the sun set over the ocean. The sky glows with warm orange, pink, and lavender tones. Waves gently roll onto the shore as the camera slowly pulls back, ending on a peaceful, atmospheric composition. Visual Style: Photorealistic travel cinematography, candid luxury lifestyle aesthetic, natural human expressions, realistic skin texture, detailed fabric movement, authentic European architecture, soft film grain, warm color grading, smooth camera tracking, shallow depth of field, natural lighting, 4K quality, vertical 9:16 format. Consistency Rules: Preserve the same woman, face, hairstyle, cream outfit, and beige tote bag in every scene. Ensure realistic walking physics, natural hand movements, consistent body proportions, smooth scene transitions, and believable lighting. Avoid flickering, face distortion, duplicate people, artificial motion, sudden outfit changes, text overlays, subtitles, and watermarks.
檢視詳情
0:30
ByteDanceSeedance 2.5
Subject: A charming 3D animated flora girl with flowing green hair, tiny flower crown, pastel-green leaf dress, and tiny boots, living in a magical garden. Style: Whimsical 3D fantasy animation, storybook aesthetics, expressive character animation, vibrant flowers, magical particles, playful physics, cinematic lighting, warm fairytale atmosphere. Camera: Macro garden shots, low angles, sweeping movements, fast tracking, gentle slow motion, and wide reveals showing her tiny scale. Scene: She waters a giant sunflower when it suddenly sneezes, launching a glowing seed into the air. She chases it across giant leaves and mushrooms, then rides a butterfly after it. The seed lands inside a giant watering can; she climbs the handle, slips, and accidentally tips it over, sending a sparkling wave of water through the garden and causing flowers to bloom everywhere. Soaked and surprised, she discovers the glowing seed has landed in her flower crown. She smiles proudly—until the entire garden suddenly sneezes, sending a huge storm of petals flying and burying her. Audio: Magical playful music, wind, birds, buzzing insects, water splashes, tiny footsteps, comedic whooshes, and a giant playful sneeze. No dialogue.
檢視詳情
0:25
ByteDanceSeedance 2.5
HOLLYWOOD CINEMATIC SEEDANCE 2.5 — ZOMBIE APOCALYPSE Create an EXACTLY 30-second ultra-photorealistic live-action Hollywood zombie-apocalypse sequence. Premium theatrical action-thriller, ARRI ALEXA 65, anamorphic cinema, realistic actors/VFX, natural motion blur, HDR, subtle film grain. HERO — image1 Use image1 ONLY for identity. Preserve 100% exact face, facial geometry, eyes, nose, lips, jawline, skin tone, hairstyle, facial hair, body proportions and physique. NO face drift, redesign, aging or different actor. Same identity in every shot. COSTUME Dark weathered tactical jacket, charcoal shirt, rugged cargo pants, combat boots, tactical gloves, worn backpack and rifle. Dusty, damaged survivor clothing. Same outfit/weapon throughout. WORLD One continuous destroyed downtown city block at late evening: ruined buildings, shattered windows, overturned cars, burning vehicles, debris, smoke and emergency lights. Cold blue-gray ambience with restrained orange firelight. ZOMBIES Photorealistic infected humans: pale skin, dirty faces, torn clothing, grime and realistic non-excessive wounds. Different appearances, aggressive but human biomechanics. No supernatural monsters. SHOT 01 | 00:00–04 Wide 24mm anamorphic. Hero hides behind overturned SUV, scanning a burning street filled with distant zombies and smoke. Slow lateral tracking. Wind, fire, distant groans, low drone. SHOT 02 | 04–07 50mm 3/4 close-up. Hero hears civilians trapped inside a destroyed storefront and turns toward them. Rapid push-in, rack focus to civilians. Blue evening + red emergency light. Cello tension. SHOT 03 | 07–10 35mm low-angle tracking. Zombies rush around corner. Hero steps between them and civilians, raising rifle. Realistic movement, smoke and firelight. Deep percussion. SHOT 04 | 10–14 50mm over-shoulder. Hero fires controlled rifle shots while protecting civilians. Realistic recoil, restrained muzzle flashes, shell casings and smoke. Rifle echoes, zombie cries, percussion intensifies. SHOT 05 | 14–18 35mm handheld arc, brief Dutch angle. Zombie attacks from behind; hero turns and narrowly avoids it as it crashes into a vehicle. Realistic impact and debris. Music drops to breathing and impact. SHOT 06 | 18–22 35mm Steadicam. Hero signals civilians to escape through side entrance while guarding the street. Warm interior vs cold exterior. Strings and restrained heroic brass. SHOT 07 | 22–26 65mm anamorphic low-angle dolly-in. Hero reaches doorway and sees an enormous zombie horde through smoke. Orange rim light, blue shadows. Dark orchestral tension rises. SHOT 08 | 26–30 28mm wide crane/dolly pull-back. Civilians escape LEFT. Hero remains alone, facing horde approaching RIGHT, slowly raising rifle. Reveal destroyed city. Full orchestral climax → deep bass → hard cut to black at 30s. CONTINUITY Same hero identity, costume, rifle, backpack, city block, overturned SUV, storefront, fires, smoke and lighting. Civilians LEFT, horde RIGHT. No location or outfit changes. TECHNICAL 30s, 24fps, 2.39:1 (16:9 if unsupported), 4K preferred, cinematic synchronized audio. NEGATIVE No identity change, face morphing, CGI/game/cartoon look, supernatural zombies, superhuman abilities, excessive gore, unrealistic movement, random camera shake, neon/oversaturated colors, text, logos, watermarks, distorted faces/hands or extra fingers. FINAL: Generate ONE continuous 30-second sequence in exact 8-shot order with seamless cinematic continuity and realistic Hollywood live-action quality.
檢視詳情
瀏覽全部 Seedance 2.5 提示詞探索AI 影片提示詞